Multilevel interactions between family and neighbourhood socioeconomic indices in childhood and later risks of self-harm and violent criminality in Denmark: a national cohort study.

BACKGROUND: A socioeconomically disadvantaged childhood has been associated with elevated self-harm and violent criminality risks during adolescence and young adulthood. However, whether these risks are modified by a neighbourhood's socioeconomic profile is unclear. The aim of our study was to compare risks among disadvantaged young people residing in deprived areas versus risks among similarly disadvantaged individuals residing in affluent areas. METHODS: We did a national cohort study, using Danish interlinked national registers, from which we delineated a longitudinal cohort of people born in Denmark between Jan 1, 1981, and Dec 31, 2001, with two Danish-born parents, who were alive and residing in the country when they were aged 15 years, who were followed up for a hospital-treated self-harm episode or violent crime conviction. A neighbourhood affluence indicator was derived based on nationwide income quartiles, with parental income and educational attainment indicating the socioeconomic position of each cohort member's family. Bayesian multilevel survival analyses were done to examine the moderating influences of neighbourhood affluence on associations between family socioeconomic position and sex-specific risks for the two adverse outcomes. FINDINGS: 1 084 047 cohort members were followed up for 12·8 million person-years in aggregate. Individuals of a low socioeconomic position residing in deprived neighbourhoods had a higher incidence of both self-harm and violent criminality compared with equivalently disadvantaged peers residing in affluent areas. Women from a low-income background residing in affluent areas had, on average, 95 (highest density interval 76-118) fewer self-harm episodes and 25 (15-41) fewer violent crime convictions per 10 000 person-years compared with women of an equally low income residing in deprived areas, whereas men of a low income residing in affluent areas had 61 (39-81) fewer self-harm episodes and 88 (56-191) fewer violent crime convictions per 10 000 person-years than men of a low income residing in deprived areas. INTERPRETATION: Even in a high-income European country with comprehensive social welfare and low levels of poverty and inequality, individuals residing in affluent neighbourhoods have lower risks of self-harm and violent criminality compared with individuals residing in deprived neighbourhoods. More research is needed to explore the potential of neighbourhood policies and interventions to reduce the harmful effects of growing up in socioeconomically deprived circumstances on later risk of self-harm and violent crime convictions. FUNDING: European Research Council, Lundbeck Foundation Initiative for Integrative Psychiatric Research, and BERTHA, the Danish Big Data Centre for Environment and Health funded by the Novo Nordisk Foundation Challenge Programme.

A multilevel Bayesian framework for predicting municipal waste generation rates.

Prediction of waste production is an essential part of the design and planning of waste management systems. The quality and applicability of such predictions depend heavily on model assumptions and the structure of the collected data. Ordinarily, municipal waste generation data are organized in hierarchical structures with municipal or county levels, and multilevel models can be used to generalize linear regression by directly incorporating the structure into the model. However, small amounts of data can limit the applicability of multilevel models and provide biased estimates. To cope with this problem, Bayesian estimation is often recommended as an alternative to frequentist estimation, such as least squares or maximum likelihood estimation. This paper proposes a multilevel framework under a Bayesian approach to model municipal waste generation with hierarchical data structures. Using a real-world dataset of municipal waste generation in Denmark, the predictive accuracy of multilevel models is compared to aggregated and disaggregated Bayesian models using socio-economic external variables. Results show that Bayesian multilevel models outperform the other models in prediction accuracy, based on the leave-one-out information criterion. A comparison of the Bayesian approach with its frequentist alternative shows that the Bayesian model is more conservative in coefficient estimation, with estimates shrinking to the grand mean and broader credible intervals, in contrast with narrower confidence intervals produced by the frequentist models.

Prediction of Autism Risk From Family Medical History Data Using Machine Learning: A National Cohort Study From Denmark.

Background: A family history of specific disorders (e.g., autism, depression, epilepsy) has been linked to risk for autism spectrum disorder (ASD). This study examines whether family history data could be used for ASD risk prediction. Methods: We followed all Danish live births, from 1980 to 2012, of Denmark-born parents for an ASD diagnosis through April 10, 2017 (N = 1,697,231 births; 26,840 ASD cases). Linking each birth to three-generation family members, we identified 438 morbidity indicators, comprising 73 disorders reported prospectively for each family member. We tested various models using a machine learning approach. From the best-performing model, we calculated a family history risk score and estimated odds ratios and 95% confidence intervals for the risk of ASD. Results: The best-performing model comprised 41 indicators: eight mental conditions (e.g., ASD, attention-deficit/hyperactivity disorder, neurotic/stress disorders) and nine nonmental conditions (e.g., obesity, hypertension, asthma) across six family member types; model performance was similar in training and test subsamples. The highest risk score group had 17.0% ASD prevalence and a 15.3-fold (95% confidence interval, 14.0-17.1) increased ASD risk compared with the lowest score group, which had 0.6% ASD prevalence. In contrast, individuals with a full sibling with ASD had 9.5% ASD prevalence and a 6.1-fold (95% confidence interval, 5.9-6.4) higher risk than individuals without an affected sibling. Conclusions: Family history of multiple mental and nonmental conditions can identify more individuals at highest risk for ASD than only considering the immediate family history of ASD. A comprehensive family history may be critical for a clinically relevant ASD risk prediction framework in the future.